cogames-agents 0.0.0.7__cp312-cp312-macosx_11_0_arm64.whl

cogames_agents/policy/nim_agents/random_agents.nim

@@ -0,0 +1,68 @@
+# This file has an example of random agents that just take random actions.
+
+import
+  std/random,
+  common
+
+type
+  RandomAgent* = ref object
+    agentId*: int
+    cfg*: Config
+    random*: Rand
+
+  RandomPolicy* = ref object
+    agents*: seq[RandomAgent]
+
+proc newRandomAgent*(agentId: int, environmentConfig: string): RandomAgent =
+  var config = parseConfig(environmentConfig)
+  result = RandomAgent(agentId: agentId, cfg: config)
+  result.random = initRand(agentId)
+
+proc reset*(agent: RandomAgent) =
+  agent.random = initRand(agent.agentId)
+
+proc step*(
+    agent: RandomAgent,
+    numAgents: int,
+    numTokens: int,
+    sizeToken: int,
+    rawObservation: pointer,
+    numActions: int,
+    agentAction: ptr int32
+) =
+  discard numAgents
+  discard numTokens
+  discard sizeToken
+  discard rawObservation
+  discard numActions
+  agentAction[] = agent.random.rand(1 .. 4).int32
+
+proc newRandomPolicy*(environmentConfig: string): RandomPolicy =
+  let cfg = parseConfig(environmentConfig)
+
+  var agents: seq[RandomAgent] = @[]
+  for id in 0 ..< cfg.config.numAgents:
+    agents.add(newRandomAgent(id, environmentConfig))
+  RandomPolicy(agents: agents)
+
+proc stepBatch*(
+    policy: RandomPolicy,
+    agentIds: pointer,
+    numAgentIds: int,
+    numAgents: int,
+    numTokens: int,
+    sizeToken: int,
+    rawObservations: pointer,
+    numActions: int,
+    rawActions: pointer
+) =
+  let ids = cast[ptr UncheckedArray[int32]](agentIds)
+  let obsArray = cast[ptr UncheckedArray[uint8]](rawObservations)
+  let actionArray = cast[ptr UncheckedArray[int32]](rawActions)
+  let obsStride = numTokens * sizeToken
+
+  for i in 0 ..< numAgentIds:
+    let idx = int(ids[i])
+    let obsPtr = cast[pointer](obsArray[idx * obsStride].addr)
+    let actPtr = cast[ptr int32](actionArray[idx].addr)
+    step(policy.agents[idx], numAgents, numTokens, sizeToken, obsPtr, numActions, actPtr)

cogames_agents/policy/nim_agents/test_agents.py

@@ -0,0 +1,53 @@
+import ctypes
+import os
+import sys
+
+import numpy as np
+
+
+def main() -> None:
+    current_dir = os.path.dirname(os.path.abspath(__file__))
+    sys.path.append(os.path.join(current_dir, "bindings/generated"))
+
+    import nim_agents as fa  # type: ignore[import-not-found]
+
+    fa.nim_agents_init_chook()
+
+    num_agents = 2
+    num_tokens = 50
+    size_token = 3
+    observations = np.zeros((num_agents, num_tokens, size_token), dtype=np.uint8)
+    actions = np.zeros(num_agents, dtype=np.int32)
+
+    policy = fa.RandomPolicy("{}")
+    subset = np.array([0, 1], dtype=np.int32)
+    subset_ptr = subset.ctypes.data_as(ctypes.POINTER(ctypes.c_int32))
+    policy.step_batch(
+        subset_ptr,
+        subset.size,
+        num_agents,
+        num_tokens,
+        size_token,
+        observations.ctypes.data,
+        num_agents,
+        actions.ctypes.data,
+    )
+    print(actions)
+
+    single_subset = np.array([0], dtype=np.int32)
+    single_ptr = single_subset.ctypes.data_as(ctypes.POINTER(ctypes.c_int32))
+    policy.step_batch(
+        single_ptr,
+        single_subset.size,
+        num_agents,
+        num_tokens,
+        size_token,
+        observations.ctypes.data,
+        num_agents,
+        actions.ctypes.data,
+    )
+    print(actions[0])
+
+
+if __name__ == "__main__":
+    main()